AITraining2U
Single Unit · SKU Co-pilot · Live Demo

Single Unit — one SKU-PILOT agent in the SKU lead’s pocket.

The portfolio demo shows what the CEO sees every morning. This page is the other end of the same operating model: the daily ranked checklist that the SKU lead at Biscuits 2L V1 sees on their phone every morning. One agent, push-only, no dashboard. Most Malaysian fmcg operators should start here.

Portfolio (CEO) Single Unit (SKU)
The Sku

Loading…

Loading…
Format
—
Staff (FTE)
—
Tier
—
Single-Unit Architecture for FMCG — one agent, push-only Show diagram ▾ Distributor sell-in Plant MES (output) Trade-promo calendar SKU-PILOT SKU Action Agent Reads signals · ranks tasks · pushes to phone DAILY CHECKLIST Ranked, dated, dismissible on the SKU lead’s phone
Three local signals → one agent → one ranked checklist. No dashboard, no chart. Push-only means the SKU lead never opens an app — the next task is just there. This is the entry-bar version of the operating model for fmcg: the other specialist agents are switched off until Phase 2.

Data inputs SKU-PILOT subscribes to

Twelve live feeds across operational systems, IoT, roster, vendor, weather, regulator, comms and competitor signals. The SKU-PILOT agent re-reads everything every 60 minutes and re-ranks the action list before the next push.

Today's SKU signals

Six derived signals the SKU-PILOT agent uses to score every candidate action. These are what the agent saw at 06:00 this morning, on the day selected in the tab strip.

Daily action checklist

Push-only. The SKU lead doesn’t pull a dashboard — these tasks land on their phone in this order. Mark them off as you go to feel the loop.
0%
0 of 0 tasks complete
Today’s shift

Today’s SKU-PILOT run log

The agent runs on a fixed schedule, not on demand. Each entry is a re-rank pass: inputs refreshed, signals recomputed, checklist re-ordered. Greyed rows are the rest of the day still to come.

How this was built

The agent reads three files of mock SKU telemetry — the same files that drive the portfolio demo. We filter to a single sku_id (SKU-00001), pick the latest three operating days, and let the agent generate its checklist deterministically from the day’s signals.

This page is intentionally tiny: about 200 lines of JavaScript, zero frameworks, one HTTP fetch per data file. The point is the operating model, not the chrome.

Source data: entities.csv · daily_signals.csv · agent_writebacks.jsonl